Max Ritter

Hey @ncbelov, sorry for the long waiting time. There have been repeated reports about issues with a newer hardware version of the Arducam and the DIY-Thermocam. I just ordered a...

@helmarw Great to hear it's working now! The 3D printed enclosure looks great and thanks for the mentioned improvements. I have widened the Lepton cutout a bit to the top...

Dear @LenzoM, there is a small parallax between Lepton and Visual camera that can't be avoided, as it depends on the distance to the target. Please check out the [manual](https://github.com/maxritter/DIY-Thermocam/blob/master/Documents/Manual_13.pdf),...

Hey @gregg26, can you please provide additional information about what is not working? Do you see any error on the screen? As long as the MLX90614 spot sensor is connected,...

Unfortunately not. I think you need to rewrite a big part of the load_caffe_weights script, as the network structure / the components do change during training and export / freezing....

Exactly. I also infered the MobileNetV2 on my Movidius stick, but found no improvement in terms of speed compared to the V1. So I ended up retraining the MobileNetV1.

Replace 'quiverboard/dist/*' with ['quiverboard/dist/*'] in setup.py, then install with "python setup.py install".

Thanks for providing those information. I will provide an official fix soon.

Just tried it out and didn't work for me: ```OpenCV(ocl4dnn): consider to specify kernel configuration cache directory via OPENCV_OCL4DNN_CONFIG_PATH parameter. OpenCL program build log: dnn/dummy Status -15: CL_COMPILE_PROGRAM_FAILURE -cl-no-subgroup-ifp [E]...

I solved it by replacing package name leptonica with libleptonica-dev